Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/jovesun-lab/arcgram/validatenpx skills add jovesun-lab/arcgram --skill validategit clone --depth 1 https://github.com/jovesun-lab/arcgramWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00111 | $0.01071 |
| Opus 5 | $0.00056 | $0.00535 |
| Sonnet 5 | $0.00022 | $0.00214 |
| Haiku 4.5 | $0.00011 | $0.00107 |
Grade A, and why
validate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validate - the combined Arcgram self-check entry
One call. Two questions answered between the siblings:
is the flow well-formed and coherent, AND do its @spec values still match the code?
Validate is a thin wrapper, not a new check. It imports Checkpoint and Reconcile untouched and composes their pure functions:
- Checkpoint (one input: the diagram) checks structure - well-formed, coherent.
- Reconcile (two inputs: diagram + code) checks values -
@specliterals == code constants.
Run both -> the diagram is a faithful, current spec. Every finding still comes from one sibling; Validate only merges, source-tags, and unions the attestation.
Code is optional
| input | what runs | clean possible? |
|---|---|---|
validate(diagram, { code }) |
Checkpoint and Reconcile | yes |
validate(diagram) (no code) |
Checkpoint only | no - values unchecked |
Without code there is nothing to reconcile, so Reconcile is not run (running it would just flag
every @spec pin as missing). Instead the value half is reported as one uncovered
value-check-not-run finding, so a structure-only run is never falsely "clean" on values - the same
anti-silent-pass rule both siblings enforce.
Locked invariant - uncovered is a third state, never a pass. A diagram-only run (no code) can
never produce an overall green clean, even when the structure is perfect. The attestation
explicitly appends | code consistency: NOT CHECKED (no code supplied), summary.codeConsistency
reads "NOT_CHECKED", and the CLI verdict is INCOMPLETE, never the word CLEAN. This guards the
exact silent-pass the family exists to prevent: claiming "checked & clean" while the code half was
never checked.
Output (same contract as both siblings, plus source)
{ findings:[{id,type,severity,note,source}], summary, attestation, clean }
self-check ran HH:MM:SS | N findings | M unchecked
sourceis"checkpoint"|"reconcile"|"validate"- so you can route a finding back to the check that raised it. Everything else (id,type,severity,note) is verbatim from the sibling.attestationis the union: N and M are the combined defect / uncovered totals. When the value half did not run it appends an explicit| code consistency: NOT CHECKED (no code supplied).clean === checkpoint.clean && reconcile.clean(identicallyN=0 && M=0);uncoveredis a third state and is never folded intoclean, so a skipped value-check is not clean.summarynests each sibling's own summary under.checkpoint/.reconcile, plusranandcodeConsistency("checked"|"NOT_CHECKED").- The full sub-results are returned verbatim on
.checkpoint/.reconcilefor a caller that wants the per-check breakdown.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 84 lines · 111 tokens per session scan A 134f64c2986f
validate is a skill published in the GitHub repository jovesun-lab/arcgram (9 stars, last pushed 15d ago), licensed Apache-2.0. It adds 111 tokens to every session and 1,071 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
comfyui-node-registry
Authoring & publishing ComfyUI custom nodes to the Comfy Registry, covering node structure, pyproject.toml spec, comfy-cli publishing, and CI.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).
chief-strategy-officer
Owns where the business plays and how it wins over a multi-year horizon — portfolio choices, corporate development, strategic partnerships, and planning under uncertainty. Use this for a decision about which markets or businesses to be in, whether to build, buy, or partner, how to allocate capital across business…
performance-analysis
Measurement approaches, profiling patterns, bottleneck identification, and optimization guidance. Use when diagnosing performance issues, establishing baselines, identifying bottlenecks, or planning for scale. Always measure before optimizing.